The Detection of Students' Abnormal Behavior in Online Exams Using Facial Landmarks in Conjunction with the YOLOv5 Models
The popularity of massive open online courses (MOOCs) and other forms of distance learning has increased recently. Schools and institutions are going online to serve their students better. Exam integrity depends on the effectiveness of proctoring remote online exams. Proctoring services powered by c...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | Arabic |
| Published: |
University of Information Technology and Communications
2023-06-01
|
| Series: | Iraqi Journal for Computers and Informatics |
| Subjects: | |
| Online Access: | https://ijci.uoitc.edu.iq/index.php/ijci/article/view/380 |
| _version_ | 1797650324940390400 |
|---|---|
| author | Muhanad Abdul Elah Alkhalisy Saad Hameed Abid |
| author_facet | Muhanad Abdul Elah Alkhalisy Saad Hameed Abid |
| author_sort | Muhanad Abdul Elah Alkhalisy |
| collection | DOAJ |
| description | The popularity of massive open online courses (MOOCs) and other forms of distance learning has increased recently. Schools and institutions are going online to serve their students better. Exam integrity depends on the effectiveness of proctoring remote online exams. Proctoring services powered by computer vision and artificial intelligence have also gained popularity. Such systems should employ methods to guarantee an impartial examination. This research demonstrates how to create a multi-model computer vision system to identify and prevent abnormal student behaviour during exams. The system uses You only look once (YOLO) models and Dlib facial landmarks to recognize faces, objects, eye, hand, and mouth opening movement, gaze sideways, and use a mobile phone. Our approach offered a model that analyzes student behaviour using a deep neural network model learned from our newly produced dataset" StudentBehavioralDS." On the generated dataset, the "Behavioral Detection Model" had a mean Average Precision (mAP) of 0.87, while the "Mouth Opening Detection Model" and "Person and Objects Detection Model" had accuracies of 0.95 and 0.96, respectively. This work demonstrates good detection accuracy. We conclude that using computer vision and deep learning models trained on a private dataset, our idea provides a range of techniques to spot odd student behaviour during online tests. |
| first_indexed | 2024-03-11T15:59:36Z |
| format | Article |
| id | doaj.art-22ce76fc2f0a47d2bb04d56007044294 |
| institution | Directory Open Access Journal |
| issn | 2313-190X 2520-4912 |
| language | Arabic |
| last_indexed | 2024-03-11T15:59:36Z |
| publishDate | 2023-06-01 |
| publisher | University of Information Technology and Communications |
| record_format | Article |
| series | Iraqi Journal for Computers and Informatics |
| spelling | doaj.art-22ce76fc2f0a47d2bb04d560070442942023-10-25T07:52:40ZaraUniversity of Information Technology and CommunicationsIraqi Journal for Computers and Informatics2313-190X2520-49122023-06-01491222910.25195/ijci.v49i1.380343The Detection of Students' Abnormal Behavior in Online Exams Using Facial Landmarks in Conjunction with the YOLOv5 ModelsMuhanad Abdul Elah Alkhalisy0Saad Hameed Abid1Informatics Institute for Postgraduate StudiesAl-Mansur University CollegeThe popularity of massive open online courses (MOOCs) and other forms of distance learning has increased recently. Schools and institutions are going online to serve their students better. Exam integrity depends on the effectiveness of proctoring remote online exams. Proctoring services powered by computer vision and artificial intelligence have also gained popularity. Such systems should employ methods to guarantee an impartial examination. This research demonstrates how to create a multi-model computer vision system to identify and prevent abnormal student behaviour during exams. The system uses You only look once (YOLO) models and Dlib facial landmarks to recognize faces, objects, eye, hand, and mouth opening movement, gaze sideways, and use a mobile phone. Our approach offered a model that analyzes student behaviour using a deep neural network model learned from our newly produced dataset" StudentBehavioralDS." On the generated dataset, the "Behavioral Detection Model" had a mean Average Precision (mAP) of 0.87, while the "Mouth Opening Detection Model" and "Person and Objects Detection Model" had accuracies of 0.95 and 0.96, respectively. This work demonstrates good detection accuracy. We conclude that using computer vision and deep learning models trained on a private dataset, our idea provides a range of techniques to spot odd student behaviour during online tests.https://ijci.uoitc.edu.iq/index.php/ijci/article/view/380facial landmarksbehaviour recognitiondlibonline proctoringdeep learning |
| spellingShingle | Muhanad Abdul Elah Alkhalisy Saad Hameed Abid The Detection of Students' Abnormal Behavior in Online Exams Using Facial Landmarks in Conjunction with the YOLOv5 Models Iraqi Journal for Computers and Informatics facial landmarks behaviour recognition dlib online proctoring deep learning |
| title | The Detection of Students' Abnormal Behavior in Online Exams Using Facial Landmarks in Conjunction with the YOLOv5 Models |
| title_full | The Detection of Students' Abnormal Behavior in Online Exams Using Facial Landmarks in Conjunction with the YOLOv5 Models |
| title_fullStr | The Detection of Students' Abnormal Behavior in Online Exams Using Facial Landmarks in Conjunction with the YOLOv5 Models |
| title_full_unstemmed | The Detection of Students' Abnormal Behavior in Online Exams Using Facial Landmarks in Conjunction with the YOLOv5 Models |
| title_short | The Detection of Students' Abnormal Behavior in Online Exams Using Facial Landmarks in Conjunction with the YOLOv5 Models |
| title_sort | detection of students abnormal behavior in online exams using facial landmarks in conjunction with the yolov5 models |
| topic | facial landmarks behaviour recognition dlib online proctoring deep learning |
| url | https://ijci.uoitc.edu.iq/index.php/ijci/article/view/380 |
| work_keys_str_mv | AT muhanadabdulelahalkhalisy thedetectionofstudentsabnormalbehaviorinonlineexamsusingfaciallandmarksinconjunctionwiththeyolov5models AT saadhameedabid thedetectionofstudentsabnormalbehaviorinonlineexamsusingfaciallandmarksinconjunctionwiththeyolov5models AT muhanadabdulelahalkhalisy detectionofstudentsabnormalbehaviorinonlineexamsusingfaciallandmarksinconjunctionwiththeyolov5models AT saadhameedabid detectionofstudentsabnormalbehaviorinonlineexamsusingfaciallandmarksinconjunctionwiththeyolov5models |